feedback 6197

Hospitals and health systems are continuously striving for the ability to identify patient activity, reduce cost, and increase the level of engagement of both the physician and the patient (Bresnick, n.d.). This is where predictive analytics comes into play, as it allows organizations/providers to use technology and statistical methods to derive insights from massive amounts of data to better understand future interactions with patients, as well as with population groups (Bresnick, n.d.). Instead of simply presenting information about past events, predictive analytics estimates the likelihood of future outcomes based on patterns in historical data and, therefore, allows clinicians, financial experts, and administrative staff to make more informed decisions on best available practices (Bresnick, n.d.). The ability of not only predicting, but also preventing, in the world of population health is of significant importance for the better management of patient outcomes, operations, clinical protocols, and utilization (Bresnick, n.d.).

Predictive analytics is, therefore, useful for: avoiding hospital re-admissions; risk scoring of chronic diseases; getting ahead of patient deterioration; forestalling appointment no-shows; predicting patient utilization patterns; managing the supply chain; ensuring strong data security; developing precision medicine/new therapies; and bolstering patient engagement and satisfaction (Bresnick, n.d.).

All things considered, healthcare organizations are using such predictive capabilities across the industry to extract actionable, forward-looking insights from their growing data assets (Bresnick, n.d.). These behavioral patterns are allowing for the creation of meaningful care plans so as to keep patients engaged with their financial and clinical responsibilities, thus resulting in increased patient activation, lower cost of care, and improved clinical outcomes across the care continuum (Bresnick, n.d.).

Reference

Bresnick, J. (n.d.). 10 high-value cases for predictive analytics in healthcare. Retrieved from https://healthitanalytics.com/news/10-high-value-use-cases-for-predictive-analytics-in-healthcare

JESSICA

Predictive analytics (PA) refers to the use of statistics and modeling to determine future performance based on current and historical data (Halton, 2019). This type of analysis allows the organization to look at the patterns presented to determine if these patterns are likely to emerge again. In healthcare, predictive analysis is used to predict outcomes for individual patients with the use of data from past treatment as well as the latest published medical research. According to Dr. Linda Winters-Miner, “Not only can PA help with predictions, but it can also reveal surprising associations in data that our human brains would never suspect” (Winters-Miner, 2014).  

The use of PA could increase the accuracy of a physician’s diagnosis for a patient. Since no two patients are the same, physicians occasionally find it difficult to provide diagnoses. If physicians were able to enter patient demographics and their symptoms into a system with a tested and accurate predictive algorithm to provide further insight, the prediction could assist the physician in many ways and increase the accuracy of diagnoses (Winters-Miner, 2014). Predictive analytics could also help with preventive medicine and public health. With early intervention, diseases can be prevented, patients can learn about their possible risks, and population disease patterns could change dramatically (Winters-Miner, 2014). Medication wise, pharmaceutical companies can use PA to best meet the needs of the public for medications (Winters-Miner, 2014). Over time, certain medications can be filtered out or brought back into the market after further development. With PA, companies can either develop new medication that is heavily needed or modify current medications on the market to better suit the population. Lastly, patients can become more knowledgeable of their health and the actions they need to take in order to achieve better health, which can then decrease the amount of time they spend at the doctors or in the hospital (Winters-Miner, 2014). Overall, PA can bring about many different changes in healthcare and I believe with the increased implementation of technology, we will see more and more predictive analytics used and developed.  

References